权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Non-Parametric Bayesian Methods for Causal Inference

用于因果推理的非参数贝叶斯方法

基本信息

批准号：
8751341
负责人：
JASON A ROY
金额：
$ 35.79万
依托单位：
UNIVERSITY OF PENNSYLVANIA
依托单位国家：
美国
项目类别：
财政年份：
2014
资助国家：
美国
起止时间：
2014-09-10 至 2018-06-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/8751341
关键词：
Accounting Adoption Affect Aging Algorithms Anti-Retroviral Agents Area Bayesian Method Behavior Therapy Behavioral Behavioral Research Categories Chronic Hepatitis C Clinical Clinical Research Code Cohort Studies Comparative Study Complex Computer software Data Development Documentation Dropout Evaluation Failure Future Goals HIV Health Hepatic Hepatitis C virus Internet Intervention Intervention Trial Journals Lead Literature Mediating Mediation Mediator of activation protein Methods Modeling Nature Observational Study Outcome Patients Performance Pharmaceutical Preparations Population Publishing Reproducibility Research Research Personnel Risk Safety Sampling Specific qualifier value Statistical Methods Survival Analysis Time Uncertainty Veterans Weight maintenance regimen Work base clinically relevant comparative effectiveness falls flexibility interest method development non-compliance novel novel strategies open source randomized trial research study simulation smoking cessation sound treatment strategy web site

项目摘要

PROJECT SUMMARY The overarching goal of this project is to develop Bayesian non-parametric (BNP) methods for estimating causal effects from complex data. We focus on two broad areas: survival analysis with time-varying treatments and mediation. For survival outcomes, we develop BNP methods for estimating causal parameters from structural nested failure time models, both for discrete and continuous-time problems. Likelihood-based methods have generally not been implemented for these models, because it would require many parametric modeling assumptions. Our BNP approach should provide greater flexibility than parametric models, while maintaining computational advantages. We will develop these methods for a wide array of scenarios (e.g., multinomial or continuous-valued treatment, known or unknown censoring times) and develop sensitivity analysis methods and informative priors related to untestable assumptions. For causal mediation analysis, we will extend our previous work in a variety of ways. Most importantly, we will weaken identifying assumptions with the inclusion of covariates in the models. In addition, we will generalize to a wider variety of outcomes and types of mediation (e.g. longitudinal or multiple mediators). We will also develop methods for handling non-ignorable dropout in settings with mediation. Our methods have broad applications, and we will utilize them to draw novel clinical inference from several behavioral intervention trials, and from a study on the hepatic safety of classes of antiretroviral medications.

项目摘要该项目的总体目标是开发贝叶斯非参数（BNP）方法，用于估计以下因素的因果效应：复杂数据我们专注于两个广泛的领域：随时间变化的治疗和调解的生存分析。为生存结果，我们开发了BNP方法来估计结构嵌套失效时间模型的因果参数，无论是对于离散和连续时间问题。基于可能性的方法通常没有被实现用于这些模型，因为它需要许多参数建模假设。我们的BNP方法应提供更大的灵活性而不是参数模型，同时保持计算优势。我们将开发这些方法，场景（例如，多项式或连续值处理，已知或未知的截尾时间）并提高灵敏度分析方法和与不可检验的假设相关的信息先验。对于因果中介分析，我们将扩展我们以前的工作以各种方式。最重要的是，我们将削弱识别假设，模型中的协变量。此外，我们将归纳到更广泛的结果和调解类型（例如，纵向或多个介质）。我们还将开发处理设置中不可识别的辍学的方法，调解我们的方法具有广泛的应用，我们将利用它们从几个方面得出新的临床推断。行为干预试验，以及抗逆转录病毒药物的肝脏安全性研究。